paper-with-me

홈 › Papers

Prompt-and-Rerank: A Method for Zero-Shot and Few-Shot Arbitrary Textual Style Transfer with Small Language Models

2022-05-23 · Mirac Suzgun, Luke Melas-Kyriazi, Dan Jurafsky

We propose a method for arbitrary textual style transfer (TST)--the task of transforming a text into any given style--utilizing general-purpose pre-trained language models. Our method, Prompt-and-Rerank, is based on a mathematical formulation of the TST task, decomposing it into three constituent components: textual similarity, target style strength, and fluency. Specifically, our method first uses zero-shot or few-shot prompting to obtain a set of candidate generations in the target style, and then re-ranks these candidates according to a combination of the three components above. Empirically, our method enables small pre-trained language models to perform on par with state-of-the-art large-scale models while consuming two orders of magnitude less compute and memory. Finally, we conduct a systematic investigation of the effect of model size and prompt design (e.g., prompt paraphrasing and delimiter-pair choice) on style transfer quality across seven diverse textual style transfer datasets.

📄 PDF Abstract BibTeX arXiv:2205.11503

Code (1)

suzgunmirac/prompt-and-rerank 공식 구현 pytorch

Tasks

Style Transfer

Similar Papers 제목 키워드 기반

Beyond Reproducibility: Advancing Zero-shot LLM Reranking Efficiency with Setwise Insertion

2025-04-09 · Jakub Podolak, Leon Peric, Mina Janicijevic, Roxana Petcu

This study presents a comprehensive reproducibility and extension analysis of the Setwise prompting methodology for zero-shot ranking with Large Language Models (LLMs), as proposed by Zhuang et al. We evaluate its effect…

Computational EfficiencyDocument RankingReranking

Scaling Down, LiTting Up: Efficient Zero-Shot Listwise Reranking with Seq2seq Encoder-Decoder Models

2023-12-26 · Manveer Singh Tamber, Ronak Pradeep, Jimmy Lin

Recent work in zero-shot listwise reranking using LLMs has achieved state-of-the-art results. However, these methods are not without drawbacks. The proposed methods rely on large LLMs with billions of parameters and limi…

DecoderReranking

RankVicuna: Zero-Shot Listwise Document Reranking with Open-Source Large Language Models

2023-09-26 · Ronak Pradeep, Sahel Sharifymoghaddam, Jimmy Lin

Researchers have successfully applied large language models (LLMs) such as ChatGPT to reranking in an information retrieval context, but to date, such work has mostly been built on proprietary models hidden behind opaque…

Information RetrievalRerankingRetrieval

Vote-in-Context: Turning VLMs into Zero-Shot Rank Fusers

2025-11-03 · Mohamed Eltahir, Ali Habibullah, Lama Ayash, Tanveer Hussain 외 arxiv

In the retrieval domain, candidates' fusion from heterogeneous retrievers is a long-standing challenge, particularly for complex, multi-modal data such as videos. While typical fusion techniques are training-free, they r…

Video Retrieval

A Recipe For Arbitrary Text Style Transfer with Large Language Models

2021-09-08 · ACL 2022 5 · Emily Reif, Daphne Ippolito, Ann Yuan, Andy Coenen 외

In this paper, we leverage large language models (LMs) to perform zero-shot text style transfer. We present a prompting method that we call augmented zero-shot learning, which frames style transfer as a sentence rewritin…

SentenceSentence ReWritingStyle TransferText Style Transfer+1